In reply to @geoffreyirving

Geoffrey Irving

Geoffrey Irving

@geoffreyirving · Twitter ·

But I just published “Automated alignment is harder than you think” (https://arxiv.org/abs/2605.06390)! Automated alignment is not the best plan! A better plan is to not build ASI yet, and the world should try hard to realise that plan. Alas, the speed of progress calls for backups.

Automated alignment involves a mixture of tasks which are easy and hard to supervise correctly, and we could easily get fooled by the later.